检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

4,884 篇 会议
91 篇 期刊文献
21 册 图书

馆藏范围

4,996 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,835 篇 工学
- 1,763 篇 计算机科学与技术...
- 1,191 篇 信息与通信工程
- 935 篇 软件工程
- 878 篇 电气工程
- 274 篇 光学工程
- 139 篇 控制科学与工程
- 129 篇 电子科学与技术（可...
- 124 篇 生物工程
- 103 篇 生物医学工程（可授...
- 99 篇 仪器科学与技术
- 85 篇 机械工程
- 68 篇 网络空间安全
- 45 篇 化学工程与技术
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 26 篇 测绘科学与技术
1,207 篇 医学
- 1,186 篇 临床医学
- 34 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
- 28 篇 特种医学
1,056 篇 理学
- 755 篇 物理学
- 299 篇 数学
- 138 篇 生物学
- 84 篇 统计学（可授理学、...
- 53 篇 系统科学
- 50 篇 化学
254 篇 管理学
- 161 篇 管理科学与工程(可...
- 100 篇 图书情报与档案管...
47 篇 军事学
- 45 篇 军队指挥学
38 篇 法学
- 34 篇 社会学
14 篇 农学
10 篇 文学
8 篇 经济学
7 篇 教育学
2 篇 艺术学

主题

562 篇 image coding
549 篇 image processing
354 篇 visual communica...
326 篇 visualization
308 篇 feature extracti...
298 篇 image segmentati...
189 篇 image reconstruc...
181 篇 cameras
178 篇 image compressio...
175 篇 humans
161 篇 video coding
161 篇 signal processin...
131 篇 image enhancemen...
131 篇 image quality
127 篇 image analysis
127 篇 image color anal...
125 篇 image edge detec...
122 篇 training
119 篇 image retrieval
107 篇 decoding

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
25 篇 school of electr...
22 篇 school of electr...
20 篇 university of sc...
18 篇 shanghai jiao to...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
13 篇 institute of ima...
12 篇 cas key laborato...
11 篇 university of el...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 school of comput...
10 篇 peking univ inst...
10 篇 tsinghua univ de...
10 篇 xidian univ sch ...
9 篇 zhejiang univers...
9 篇 microsoft res as...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 guangtao zhai
22 篇 li sumei
19 篇 li song
18 篇 li li
18 篇 min xiongkuo
16 篇 andré kaup
16 篇 dong liu
16 篇 shan liu
15 篇 yang xiaokang
14 篇 chen zhibo
14 篇 gao wen
13 篇 xie rong
13 篇 xiongkuo min
12 篇 kaup andre
11 篇 heming sun
11 篇 zhibo chen
11 篇 zhenzhong chen

语言

4,898 篇 英文
64 篇 土耳其文
31 篇 中文
20 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2007"

共 4996 条记录，以下是901-910 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

An Improved Ultra-High Definition Panoramic Video Mosaic Method for Airport Scene 8

An Improved Ultra-High Definition Panoramic Video Mosaic Met...

引用

8th IEEE International conference on Computer and communications, ICCC 2022

作者： Wang, Kai Yang, Tao Zhang, Xiaohai Tang, Mozhen The 2nd Research Institute Civil Aviation Administration of China Chengdu China Beijing Capital International Airport Co. Ltd Beijing China

ISBN: (纸本)9781665450515

In the airport flight area video surveillance system, in order to solve the problems of low image resolution, mosaic fusion with ghosting and high processing time in multi-channel 4K High Definition (HD) video image stitching, an improved ultra-high definition panoramic video mosaic method for airport scene is proposed. Firstly, Improved Harris algorithm is used to extract the feature point of each image and the Euclidean distance is used to match feature vector. In addition, Gaussian feature of nonlinear weighted mask is calculated disposable and two-level of Gaussian pyramid is used for smoothing, besides, the original image and the smoothed image are directly used for the accumulation and difference. At the same time, because the overlapping part is divided into regions similar to Gaussian scale smoothing and Gaussian smoothing of mask, the transition effect is more natural and smooth during image mosaic and fusion. Finally, video image mosaic and fusion is realized and panoramic video image resolution can be up to 8K (ultra-high definition). The experiment at typical airport shows that the improved method meets the high-quality efficiency of visible video image stitching and fusion. © 2022 IEEE.

关键词： image resolution

来源：评论

学校读者我要写书评

暂无评论

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Based image Classification

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Ba...

引用

International conference on Information Science and communications Technologies (ICISCT)

作者： Arpanpreet Kaur Amit Kumar Mishra Bura Vijay Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (数字)9798331527921

ISBN: (纸本)9798331527938

Considered as two varieties: damaged and undamaged, almonds are a rather consumed agricultural product. Maintaining consumer satisfaction and industry standards depends on good detection of damaged almonds., which could be influenced by mechanical damage., mold, or pests. On the other hand, slow, labor-intensive hand inspection methods prone to mistake demand automated classification systems. This work meets that demand by automating the categorization process using DenseNet-121, a convolutional neural network (CNN), therefore lowering labor expenses and increasing accuracy. Particularly considering the tiny dataset of 1,000 photos split equally between damaged and undamaged almonds, DenseNet-121's architecture-with its dense connections and capacity to reuse features-is well-suited for the almond classification challenge. Pre-trained on imageNet and polished for this particular purpose, the model-trained across 60 epochs using a 32-batch size-achieved an accuracy of 95.27%. Random horizontal flips, resizing., and center cropping among other data augmentation techniques improved the model's generalizing capability. This work demonstrates the model's ability to substitute human methods in actual environments by showing how well it employs little visual information to classify almonds. Automating almond sorting speeds and provides higher consistency in quality control as well as efficiency of sorting. This work opens the road for further research of machine learning techniques in agricultural processing with possible applications in food quality assurance.

关键词： Accuracy Quality assurance Process control Quality control Machine learning Data augmentation Data models Convolutional neural networks Sorting image classification

来源：评论

学校读者我要写书评

暂无评论

visual Data Enciphering via DNA Encoding, S-Box, and Tent Mapping

Visual Data Enciphering via DNA Encoding, S-Box, and Tent Ma...

引用

International image processing, Applications and Systems conference (IPAS)

作者： Mohamed Gabr Hana Younis Marwa Ibrahim Sara Alajmy Wassim Alexan Faculty of MET The German University in Cairo Cairo Egypt Faculty of IET The German University in Cairo Cairo Egypt

ISBN: (纸本)9781665462204

The ever-evolving nature of the Internet and wireless communications, as well as the production of huge amounts of multimedia every day has created a dire need for their security. In this paper, an image encryption technique that is based on 3 stages is proposed. The first stage makes use of DNA encoding. The second stage proposed and utilizes a novel S-box that is based on the Mersenne Twister and a linear descent algorithm. The third stage employs the Tent chaotic map. The computed performance evaluation metrics exhibit a high level of achieved security.

关键词： Wireless communication Performance evaluation visualization image coding Chaotic communication DNA Production

来源：评论

学校读者我要写书评

暂无评论

The Potential Utility of image Descriptions: User Identity Linkage across Social Networks Based on MultiModal Self-Attention Fusion

The Potential Utility of Image Descriptions: User Identity L...

引用

IEEE International conference on Performance, Computing and communications (IPCCC)

作者： Yunfeng Li Gaopeng Gou Gang Xiong Zhen Li Mingxin Cui Chinese Academy of Sciences Institute of Information Engineering School of Cyber Security University of Chinese Academy of Sciences

The task of user identity linkage across social networks aims to predict whether users from different social networks refer to the same person. This task plays a crucial role in cross-social network information dissemination and intelligent recommendations. However, existing user identity linkage tasks suffer from several challenges: 1) excessive reliance on social network topology, neglecting users’ visual modality information; 2) inadequate handling of noise in user feature data; and 3) ineffective fusion of users’ multimodal information. To address these issues, we investigated a method that utilizes heterogeneous multimodal posts, including user-generated text, images, and check-in messages, to achieve user identity linkage across social networks. We innovatively leveraged a pre-trained model for image-to-text conversion to further explore users’ image data and proposed an adversarial learning model based on the multimodal self-attention mechanism (AMSA). The AMSA model consists of four components: user feature extraction, user feature processing, user feature fusion, and adversarial learning. Specifically, AMSA initially employed advanced pre-trained models to extract features from multiple modalities of users, including images and text. Subsequently, it utilized multiple mechanisms, such as multi-head self-attention, to process data from each modality separately and then fused them into user representation vectors. Finally, AMSA employed adversarial learning to enhance the model’s learning capacity and mitigate semantic disparities in user information across different platforms. We conducted model performance evaluations on publicly available datasets, and experimental results demonstrated the superiority of the proposed AMSA model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Garment Suggestion Engine Based on visual Similarity 28

A Garment Suggestion Engine Based on Visual Similarity

引用

28th Signal processing and communications Applications conference (SIU)

作者： Gokturk, Mehmet Kabakli, Bilal Yogurtcuglu, Hamza Gebze Tech Univ Dept Comp Sci Gebze Turkey Modanisa AS R&D Ctr Istanbul Turkey

ISBN: (纸本)9781728172064

In this study, a product suggestion engine has been developed for an e-commerce site portfolio focusing on garment items. Traditional collaborative filtering methods usually lack applicability due to high turnover rates in product lists. Thus, by focusing on visual similarity using deep leraning technique successful results were obtained and it has been concluded that application of this technique to real live e-commerce garment site will be suitable.

关键词： deep learning e-commerce image processing

来源：评论

学校读者我要写书评

暂无评论

Compression and Transmission of 8K Stereoscopic VR Using VAE-GAN Latents and Standard Encoders

Compression and Transmission of 8K Stereoscopic VR Using VAE...

引用

IEEE conference on Wireless communications and Networking

作者： Sampreet Vaidya Hatem Abou-Zeid Diwakar Krishnamurthy Department of Electrical and Software Engineering University of Calgary Calgary AB Canada

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Despite the heightened popularity of Virtual Re-ality (VR), streaming high-resolution stereoscopic VR remains a challenge. This is primarily due to significant bandwidth demands of high-definition VR content. While advanced deep neural networks (DNN s) have demonstrated the potential to outperform standard codecs, their integration into real-world transmission frameworks is complex and not directly compatible with current encoding standards. To bridge this gap, this paper proposes a novel technique for compressing and transmitting 8K stereoscopic scenes using Variational Autoencoder (VAE) GAN latents represented as 3-channel RGB scenes that can be transmitted via standard encoders. The proposed method reduces bandwidth requirements by 45.1 % across different 8K scenes while maintaining visual quality, highlighting the effectiveness of the approach. This study also investigates the impact of varying patch-sizes of input frames for model training and evaluate its influence on client-side reconstructions. We then explore various transmission configurations of latent frames. Our findings suggest that while residual transmission offers limited benefits for 3-channel latent frame compression, raw transmission consistently yields better results, particularly for texture-heavy scenes. To the best of our knowledge, this is the first such transmission study on 8K stereoscopic scenes for cloud-based VR, providing valuable insights for optimizing high-resolution VR streaming systems. Code: ***/sampreetucalgary07/8K-VR-compression.

关键词： Training Cloud computing visualization Solid modeling Stereo image processing Bandwidth Virtual reality Streaming media Generative adversarial networks Standards

来源：评论

学校读者我要写书评

暂无评论

Deep Learning: A Detailed Analysis Of Various image Augmentation Techniques

Deep Learning: A Detailed Analysis Of Various Image Augmenta...

引用

Networking and communications (ICNWC), International conference on

作者： S. Swathi M. Rajalakshmi Vijayalakshmi Senniappan Department of Computer Science and Engineering Sri Sairam Institute of Technology Chennai India Department of Information Technology Coimbatore Institute of Technology Coimbatore India Department of Information Technology Park College of Engineering & Tech Coimbatore India

Deep learning has been performing reasonably well in computer vision tasks that call for a high volume of photos, although gathering images is often expensive and challenging. Different picture augmentation techniques have been put forth as practical and efficient solutions to this problem Understanding current algorithms is critical when developing new processes or determining the best approaches for a certain task. With deep learning, some of the data pre-processing that is typically required for machine learning is avoided. Unstructured text and visual data can be handled by these algorithms, which can also automate feature extraction and lessen the need for human experts. With a brand-new taxonomy of usable data, we undertake a complete survey of picture augmentation for deep learning in this work. We discuss the difficulties in computer vision tasks and vicinity distribution to give you a fundamental understanding of why we want picture augmentation. Based on the study, we think that our survey provides a clearer knowledge that may be used to select the best techniques or create original algorithms for real-world uses.

关键词： Deep learning Surveys Computer vision visualization Machine learning algorithms Taxonomy Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On 2D-3D image Feature Detections for image-To-Geometry Registration in Virtual Dental Model

On 2D-3D Image Feature Detections for Image-To-Geometry Regi...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Tang, Hui Hsung, Tai-Chiu Lam, Walter Y. H. Cheng, Leo Y. Y. Pow, Edmond H. N. Guangdong Univ Technol Sch Informat Engn Guangzhou Peoples R China Univ Hong Kong Fac Dent Hong Kong Peoples R China

ISBN: (纸本)9781728180687

3D digital smile design (DSD) gains great interest in dentistry because it enables esthetic design of teeth and gum. However, the color texture of teeth and gum is often lost/distorted in the digitization process. Recently, the image-to-geometry registration shade mapping (IGRSM) method was proposed for registering color texture from 2D photography to 3D mesh model. It allows better control of illumination and color calibration for automatic teeth shade matching. In this paper, we investigate automated techniques to find the correspondences between 3D tooth model and color intraoral photographs for accurately perform the IGRSM. We propose to use the tooth cusp tips as the correspondence points for the IGR because they can be reliably detected both in 2D photography and 3D surface scan. A modified gradient descent method with directional priority (GDDP) and region growing are developed to find the 3D correspondence points. For the 2D image, the tooth tips contour lines are extracted based on luminosity and chromaticity, the contour peaks are then detected as the correspondence points. From the experimental results, the proposed method shows excellent accuracy in detecting the correspondence points between 2D photography and 3D tooth model. The average registration error is less than 15 pixels for 4752x3168 size intraoral image.

关键词： 3D digital smile design image to geometry registration Tooth Shade Intraoral scan Range image

来源：评论

学校读者我要写书评

暂无评论

Multi-Sensor Fusion SLAM Based on Fast Euclidean Clustering to Filter Dynamic Targets

Multi-Sensor Fusion SLAM Based on Fast Euclidean Clustering ...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Ming Geng Yongxing Jia Xiaojian Qian Ziang Zhao College of Communications Engineering Army Engineering University of PLA Nanjing China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

R3LIVE is a new multi-sensor fusion SLAM framework, which mainly uses the three sensors of lidar, camera and IMU to realize the effective fusion of heterogeneous data through the error state iterative Kalman filtering method, so as to achieve the function of efficient and accurate simultaneous positioning and mapping. Specifically, this system uses lidar and IMU to construct laser inertial odometer (LIO) to construct the geometry of the external environment, and also it builds a visual inertial odometer (VIO) with a camera and IMU to reconstruct a dense RGB map of the environment. However, in the face of the environment where dynamic objects appear, the positioning accuracy of the system will be affected due to the point cloud of the sensor on the dynamic objects. Moreover, the continuous point cloud of the dynamic objects will cause continuous “ghost” in the dense RGB map constructed. In order to solve the above problems, a fast Euclidean clustering algorithm is proposed to filter out dynamic targets, that is, before the LIO system laser point cloud registration, the input point cloud is initially classified by using a fast Euclidean clustering algorithm, and the original point cloud is divided into ground points, background points and foreground points, among which the ground points and background points are usually considered static points. The foreground points may be either dynamic or static points. Then, the viewpoint visibility method is used for the foreground points to further verify the existence of dynamic points, and the dynamic points in the foreground points are filtered out. Finally, a widely distributed sparse extraction method is designed to solve the problem of excessive extraction of surface features in scenes with rich structure and texture. This enhances the real-time performance and robustness of the system in dynamic scenarios.

关键词： Point cloud compression visualization Accuracy Simultaneous localization and mapping Heuristic algorithms Clustering algorithms Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Symposium on Parallel and Distributed processing with Applications and IEEE International conference on Ubiquitous Computing and communications (ISPA/IUCC)

作者： Hui Guo Di Xie Jiahao Pang Jie He Caixu Xu Xuejian Zhang Minglang Chen Faculty of Arts and Humanities Macao University of Science and Technology Wuzhou China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China college of Electronical and Information Engineering Wuzhou University Wuzhou China

At present, the self-similarity of images has received wide attention in many fields such as image compression. Most of the images have strong self-similarity through the human eye visual system observation. However, the special images with strong self-similarity for human eye observation such as biomicroscopy are not digitally reflected by a certain algorithm, this paper proposes a self-similarity coefficient algorithm that is applicable to special natural images such as biomicroscopy and aerial photography, which has high self-similarity coefficients for biomicroscopy and other images.

关键词： Photography image coding Microscopy visual systems Ubiquitous computing Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 87 88 89 90 91 92 93 94 95 96 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：